bert-base-cased-finetuned-products_2

This model is a fine-tuned version of amirkazemim/bert-base-cased-finetuned-products on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.3615

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 4e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss
0.7101	1.0	7595	2.2779
0.6524	2.0	15190	2.3167
0.5332	3.0	22785	2.3597
0.4328	4.0	30380	2.4146
0.3567	5.0	37975	2.5220
0.2966	6.0	45570	2.6249
0.2434	7.0	53165	2.7248
0.2002	8.0	60760	2.8240
0.1727	9.0	68355	2.9580
0.1407	10.0	75950	3.0205
0.1192	11.0	83545	3.1544
0.1031	12.0	91140	3.2085
0.0864	13.0	98735	3.2532
0.0735	14.0	106330	3.3022
0.064	15.0	113925	3.3487
0.0508	16.0	121520	3.3615

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0.post100
• Datasets 2.19.1
• Tokenizers 0.19.1